Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    alloys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rack
    -0.29
    æĶ»
    -0.27
     takeover
    -0.26
    รà¸Ńà¸ļ
    -0.26
     protester
    -0.26
     PartialView
    -0.25
     Semantic
    -0.25
    æĶ»åĩ»
    -0.25
     poll
    -0.25
    èĭŀ
    -0.25
    POSITIVE LOGITS
    coin
    0.27
    æĿIJè´¨
    0.27
     denomination
    0.26
    ircular
    0.25
    çĶµå·¥
    0.25
    ValueType
    0.25
    大人
    0.25
    æľªæĪIJ
    0.24
    fabric
    0.24
    åı·çłģ
    0.24
    Act Density 0.007%

    No Known Activations